Real Skill packageSource verifiedClawHub registry

詹明明·做成一个技能

把这次会话里已经跑通的做法固化成一个新技能。不是从想法造技能——是从**已经产生过正确结果的那一段过程**里提炼，所以只在事情做完之后用。 触发方式：/zmm-skillify、/固化、/做成技能、/zmm-固化、「这次的做法留下来」「把刚才那套变成技能」「下次别再重新想一遍」「这个流程以后还要用」 Turn a method that already worked in this session into a reusable skill. Extracts from a completed run, never from an idea — so it only fires after the work is done. Trigger: /zmm-skillify, "make this a skill", "save this workflow", "I don't want to re-derive this next time"

Identity and source

Publisher attribution詹明明registry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 55% rule confidence
Package forminstruction bundle2 recorded files
Canonical sourceClawHub registryclawhub:iamzifei:zmm-skillify
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/2/2026.claude/skills/zmm-skillify

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/2/2026.agents/skills/zmm-skillify

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/2/2026skills/zmm-skillify

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @iamzifei/zmm-skillify
clawhub inspect @iamzifei/zmm-skillify --version 0.1.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
2 / 2 inspected as text
Checked
9/2/2026, 4:32:29 AM
Scanner
0.1.3
Policy
1.0.3
1 inferred permission indicators
  • network access — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/1/2026, 4:50:56 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: clean
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:b3c28e7f6b105faec3ab3660185f6b859b30e821873fd0f08351ed74197f86b0
Show up to 2 recorded paths
  • skill-card.md
  • SKILL.md

Source changelog

新增「做成一个技能」；新手指南命令与出口；豆包安装配截图 新技能 zmm-skillify · 詹明明·做成一个技能（21 个） 把本次会话里已经跑通的做法固化成新技能。参考 dbs-skill-maker 的方法骨架， 但按本家族的判据文化改写，三处不同： ① 硬门禁：没做完的 / 没验证过的 / 不会再发生的，一律不给固化 —— 固化没验证的经验等于把猜测写成规则。用户说「做成技能」也不跳过门禁。 ② 提炼源按可信度排序：本次实际过程 > 技能记忆 > 用户口述的「我一般怎么做」。 口述可信度最低，人对自己流程的描述常和实际不一样；三者冲突以实际过程为准， 且冲突本身往往就是最值钱的那条规则。 ③ 每条规则必须带 🟢实测 / 🟡推断 / ⚪猜测 等级，🟡 要补「如果错了最可能错在哪」。 自检清单里加了「跟现有技能有没有职责重叠」——重叠就改那个，不新建。 交付默认只到本地可用，发布是另一件事，需明确授权。 新手指南 触发词补 /zmm 新手指南、/zmm 上手。 第 5 幕加「选 1 之后直接送进完整流程」——演示完人还在原地，引导就白做了。 给了按第 1 幕答案分流的对照表，并写明它是「通常」不是路由规则， 真正的选择仍走 Step 3–5 的动态发现与筛选。 README 新增「装完不知道说什么」一节：/zmm 新手指南 的五步流程， 外加两组可直接照说的原话（做内容 8 条 / 管生意 8 条）。 豆包安装配了两张截图（+新建菜单、上传技能对话框）。 ⚠️ 截图是从用户提供的原图裁出来的：原图带侧边栏对话历史与账号名，已裁掉，只留 UI。